In the news
HARP: Training-Free Dual-Profile Agentic Communication for LLM-Based Recommendation
arXiv cs.AI · Published · 3 min read
In 30 seconds
- What happened
- HARP adds three operators to frozen LLM recommendation systems: symmetric item profiles, retrieval-level homophily matching, and reflective profile updates without retraining.
- Why it matters
- Engineers building LLM-based recommenders who want better ranking accuracy without modifying the base model or retraining.
- Watch out
- The method requires access to item metadata for profile extraction and adds computational cost during retrieval; gains vary across datasets.
- agent
- agentic
- llm
- reranker
- prompt
The patterns behind this
Each one covers how the technique works, when it earns its cost, and where it breaks.
The Agent Architect
One pattern, one tradeoff, one production failure story. A short weekly briefing for people building agentic systems.
Weekly email, one-click unsubscribe. We only use your address to send the briefing.